Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    of course

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    上半年
    0.81
    ronectin
    0.80
     September
    0.78
     وذلك
    0.75
    /'
    0.73
    單
    0.73
     Dedicated
    0.72
     대하여
    0.70
     August
    0.70
     July
    0.70
    POSITIVE LOGITS
     course
    0.77
    course
    0.71
    Course
    0.69
    તિ
    0.66
     COURSE
    0.66
    늦
    0.63
     Course
    0.63
    ayat
    0.60
    ించాలి
    0.59
    γή
    0.59
    Act Density 0.056%

    No Known Activations